Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    latest/earliest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mend
    -0.07
     Mental
    -0.06
     만족
    -0.06
     Kw
    -0.06
     налог
    -0.06
    ObjectOfType
    -0.06
     dissert
    -0.06
     suspected
    -0.06
    Kat
    -0.06
    血
    -0.06
    POSITIVE LOGITS
     explicitly
    0.07
    (in
    0.06
    0.06
     yapıyor
    0.06
    >No
    0.06
    ระยะ
    0.06
    ้อง
    0.06
     Archie
    0.06
    .CreateInstance
    0.06
    (http
    0.06
    Act Density 0.043%

    No Known Activations